Search Results
| Search type | Search syntax |
|---|---|
| Tags | [tag] |
| Exact | "words here" |
| Author |
user:1234 user:me (yours) |
| Score |
score:3 (3+) score:0 (none) |
| Answers |
answers:3 (3+) answers:0 (none) isaccepted:yes hasaccepted:no inquestion:1234 |
| Views | views:250 |
| Code | code:"if (foo != bar)" |
| Sections |
title:apples body:"apples oranges" |
| URL | url:"*.example.com" |
| Saves | in:saves |
| Status |
closed:yes duplicate:no migrated:no wiki:no |
| Types |
is:question is:answer |
| Exclude |
-[tag] -apples |
| For more details on advanced search visit our help page | |
Results tagged with machine-learning
Search options not deleted
user 49646
Machine learning algorithms build a model of the training data. The term "machine learning" is vaguely defined; it includes what is also called statistical learning, reinforcement learning, unsupervised learning, etc. ALWAYS ADD A MORE SPECIFIC TAG.
3
votes
Accepted
How does neural network training work, if there are A HUGE number of points that not differe...
The simple and perhaps unsatisfying answer is that we arbitrarily choose a gradient at 0.
Typically deep learning libraries will choose to have a gradient of 0. We can see this using the python libra …
- 1,447
4
votes
Automated ML vs the entire replicability/reproducibility crisis
I agree with Alex R's comments, and I'm expanding them into a full answer.
I'll be talking about "black box" models in this answer, by which I mean machine learning (ML) models whose internal impleme …
- 1,447
1
vote
Why does using pseudo-labeling non-trivially affect the results?
Warning, I am not an expert on this procedure. My failure to produce good results is not proof that the technique cannot be made to work. Furthermore, your image has the general description of "semi-s …
- 1,447
0
votes
Can an ML model choose between an arbitrary set of classes?
You are asking how to deal with sets of inputs instead of vectors/matrices which is the much more usual case. I will be using Deep Sets by Zaheer et al. (https://arxiv.org/abs/1703.06114) as a jumping …
- 1,447
1
vote
Use of stack of tanh layers
In your linked paper (you should provide the full citation to avoid link rot) we see the following
Our neural network classifier, depicted in Figure 3 (and based
on a one-layer model in …
- 1,447
1
vote
Accepted
Accelerating multi-label classification using NNs
I use sigmoid when there are an arbitrary number of possible labels. In your case, you know you have exactly two labels. I would instead use softmax and divide the true label by two, for example [0,.. …
- 1,447
1
vote
Normalisation of an 'image' when pixel intensities are unbounded
Use a transformation that sends unbounded values to a bounded interval. For example, the sigmoid function, tanh, etc.
After that you may perform any additional transformations needed to get your valu …
- 1,447
1
vote
0
answers
662
views
Intuition on One Class Support Vector Machines [duplicate]
I am having trouble understanding how one-class SVMs work. They were introduced in a paper by Scholkopf and others (and can be found here).
One-class SVMs perform "novelty detection", where a point i …
- 1,447
7
votes
Accepted
RNN vs Convolution 1D
Yes the interpretation of the dimensions is pretty similar in both cases.
An important case where RNNs are easier to use is with data of unknown lengths. For example, in sentence translation (e.g. t …
- 1,447
1
vote
Accepted
Is it possible to convert 3D image to 1D vector?
Yes. That is a valid transformation if you are feeding to a fully connected NN.
- 1,447
1
vote
CNN for a regression problem
I suggest you use a type of UNet (https://arxiv.org/abs/1505.04597). This kind of architecture has downsampling layers, followed by up sampling layers to get back to the original spatial dimensions.
- 1,447
4
votes
Accepted
Can a Fully Connected layer transform a 4D tensor to a 3D tensor by itself?
You are correct, Fully Connected (FC) layers have no concept of dimensionality.
However, if I wanted to use a FC layer passing into another layer which had specific dimensionality requirements, I wou …
- 1,447